Joint training of expanded end-to-end DNN for text-dependent speaker verification

We propose an expanded end-to-end DNN architecture for speaker verification based on b-vectors as well as d-vectors. We embedded the components of a speaker verification system such as modeling frame-level features, extracting utterance-level features, dimensionality reduction of utterancelevel features, and trial-level scoring in an expanded end-toend DNN architecture. The main contribution of this paper is that, instead of using DNNs as parts of the system trained independently, we train the whole system jointly with a finetune cost after pre-training each part. The experimental results show that the proposed system outperforms the baseline dvector system and i-vector PLDA system.